07.11.2005 15 s.t.
Learning Visual Features for Detection, Recognition and Action
by Dr. Justus H. Piater
from Institut Montefiore, B28, Université de Liège, Belgium
Seminarraum Haus 2, 4. Stock (Bunsenstr.)
Objects and scenes can be visually characterized by localized features and their appearance, plus the spatial relations between them. I present our recent work on learning hierarchical representations for such features based on statistics of feature cooccurrences. The learned features combine view-specific aspects within a single graphical model. Their hierarchical structure as well as bottom-up and top-down evidence integration using Nonparametric Belief Propagation loosely resemble that of higher biological visual systems. I will discuss examples of unsupervised learning for detection and recognition, and of feature learning during and for closed-loop interaction.
back to overview